Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code/technical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愈发
    -0.08
     Maxim
    -0.08
     acesso
    -0.08
     helicopter
    -0.07
     overcrow
    -0.07
    issor
    -0.07
     Hof
    -0.07
     Tax
    -0.07
    粗糙
    -0.07
    .AddWithValue
    -0.06
    POSITIVE LOGITS
    <object
    0.07
    Injected
    0.07
    Ք
    0.07
    compressed
    0.07
     Chỉ
    0.06
    Favorites
    0.06
    下來
    0.06
    ables
    0.06
    paused
    0.06
    无论是
    0.06
    Act Density 0.000%

    No Known Activations